transformers
add PocketTTSAudioTokenizer
#49588
Open
Overview
Commits
17
Changes
View On GitHub

add PocketTTSAudioTokenizer #49588

eustlb wants to merge 17 commits into mimi-sep-encoder-decoder from add-pocket-tts-audio-tokenizer
eustlb
eustlb eustlb added New model
eustlb eustlb added Audio
eustlb eustlb force pushed from d2f30881 to f931f314 2 days ago
eustlb eustlb force-pushed the mimi-sep-encoder-decoder branch from 4a12d24e to 387d6d9d 2 days ago
eustlb eustlb force pushed from f931f314 to b8254d5b 2 days ago
eustlb eustlb force pushed from b8254d5b to c62cee6b 2 days ago
eustlb eustlb force pushed from c62cee6b to def770bc 2 days ago
eustlb eustlb force pushed from def770bc to 23ad989c 2 days ago
eustlb eustlb force pushed from d581e8ec to fc5202fe 2 days ago
eustlb eustlb force-pushed the mimi-sep-encoder-decoder branch from a8d40417 to 27815fe9 2 days ago
eustlb eustlb force pushed from fc5202fe to 3b6db639 1 day ago
eustlb eustlb force pushed from 3b6db639 to b37a43bd 1 day ago
eustlb eustlb force pushed from b37a43bd to 5d0fc588 1 day ago
eustlb eustlb force pushed from 5d0fc588 to 884923d3 1 day ago
eustlb eustlb force pushed from 884923d3 to ac651f9f 1 day ago
eustlb add PocketTTSAudioTokenizer
afa5d737
eustlb nit
01908f3b
eustlb [pocket_tts_audio_tokenizer] flat config, modular over MimiConfig
29167ab8
eustlb [pocket_tts_audio_tokenizer] follow Mimi: drop the sub_configs TODO
434b776f
eustlb [pocket_tts_audio_tokenizer] inherit Mimi's resnet block and SEANet e…
778f80f7
eustlb [mimi] latent_stride / latent_dim config properties for the downsampl…
024c1439
eustlb [modular] a modular attribute overrides an inherited method of the sa…
1ffd667f
eustlb [pocket_tts_audio_tokenizer] inherit MimiEncoderModel / MimiDecoderModel
d14b92cb
eustlb [pocket_tts_audio_tokenizer] regenerate after Mimi's output capturing
b254a1f4
eustlb [pocket_tts_audio_tokenizer] inherit Mimi's encoder / decoder forward
edaa3a76
eustlb [mimi] generic docstrings for the encoder / decoder halves, quantizer…
13ba737a
eustlb [pocket_tts_audio_tokenizer] half configs, submodules, outputs and co…
15783ad3
eustlb nit
07f43ad8
eustlb eustlb force-pushed the mimi-sep-encoder-decoder branch from 22c4457b to c5039e7a 14 hours ago
eustlb eustlb force pushed from ac651f9f to 07f43ad8 14 hours ago
eustlb revert modular converted change
08516b94
eustlb [pocket_tts_audio_tokenizer] latent_stride / latent_dim fields replac…
b217d9b3
github-actions
github-actions commented on 2026-10-16
eustlb eustlb marked this pull request as ready for review 13 hours ago
eustlb clean tests
cbb1bf14
eustlb update tests
1f1613fd
github-actions
github-actions

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
New model Audio
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum